nf-core · jeffe107 · Dec 1, 2025 · Sep 16, 2025 · Sep 17, 2025 · Sep 17, 2025
@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - [#905](https://github.com/nf-core/mag/pull/905) - Add nf-test snapshot for `test_assembly_input` profile (by @dialvarezs)
 - [#930](https://github.com/nf-core/mag/pull/930) - Add binner SemiBin2 (by @d4straub)
+- [#861](https://github.com/nf-core/mag/pull/861) - Added `--generate_bigmag_file` to execute the bigmag workflow that generates the file to be used as input for [BIgMAG](https://github.com/jeffe107/BIgMAG) (added by @jeffe107)
 
 ### `Changed`
 

@@ -94,6 +94,10 @@
 
   > Orakov, A., Fullam, A., Coelho, A. P., Khedkar, S., Szklarczyk, D., Mende, D. R., Schmidt, T. S. B., and Bork, P.. 2021. “GUNC: Detection of Chimerism and Contamination in Prokaryotic Genomes.” Genome Biology 22 (1): 178. doi: 10.1186/s13059-021-02393-0.
 
+- [BIgMAG](https://doi.org/10.12688/f1000research.152290.2)
+
+  > Yepes-García, J., Falquet, L. (2024). Metagenome quality metrics and taxonomical annotation visualization through the integration of MAGFlow and BIgMAG. F1000Research 13:640. doi.org/10.12688/f1000research.152290.2
+
 - [MaxBin2](https://doi.org/10.1093/bioinformatics/btv638)
 
   > Yu-Wei, W., Simmons, B. A. & Singer, S. W. (2015) MaxBin 2.0: An Automated Binning Algorithm to Recover Genomes from Multiple Metagenomic Datasets. Bioinformatics 32 (4): 605–7. doi: 10.1093/bioinformatics/btv638.

@@ -16,12 +16,15 @@
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
 [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)
 [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)
+
 [![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/mag)
 
 [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23mag-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/mag)[![Follow on Bluesky](https://img.shields.io/badge/bluesky-%40nf__core-1185fe?labelColor=000000&logo=bluesky)](https://bsky.app/profile/nf-co.re)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)
 
 ![HiRSE Code Promo Badge](https://img.shields.io/badge/Promo-8db427?label=HiRSE&labelColor=005aa0&link=https%3A%2F%2Fgo.fzj.de%2FCodePromo)
 
+[![Static Badge](https://img.shields.io/badge/%F0%9F%8D%94%20%20BIgMAG-compatible-%2324B064)](https://github.com/jeffe107/BIgMAG)
+
 ## Introduction
 
 **nf-core/mag** is a bioinformatics best-practise analysis pipeline for assembly, binning and annotation of metagenomes.
@@ -97,6 +100,7 @@ Other code contributors include:
 - [Greg Fedewa](https://github.com/harper357)
 - [Vini Salazar](https://github.com/vinisalazar)
 - [Alex Caswell](https://github.com/AlexHoratio)
+- [Jeferyd Yepes](https://github.com/jeffe107)
 
 Long read processing was inspired by [caspargross/HybridAssembly](https://github.com/caspargross/HybridAssembly) written by Caspar Gross [@caspargross](https://github.com/caspargross)
 

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+## Originally written by Jeferyd Yepes and released under the MIT license.
+## See git repository (https://github.com/nf-core/mag) for full license text.
+
+import pandas as pd
+import re
+import argparse
+import sys
+import warnings
+
+def parse_args(args=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-s", "--summary", metavar="FILE", help="Pipeline summary file.")
+    parser.add_argument("-g", "--gunc_summary", metavar="FILE", help="GUNC summary file.")
+
+    parser.add_argument(
+        "-o",
+        "--out",
+        required=True,
+        metavar="FILE",
+        type=argparse.FileType("w"),
+        help="Output file containing final bigmag summary.",
+    )
+    return parser.parse_args(args)
+
+
+def main(args=None):
+    args = parse_args(args)
+
+    if (
+        not args.summary
+        and not args.gunc_summary
+    ):
+        sys.exit(
+            "No summary specified! "
+            "Please specify the pipeline summary and the GUNC summary."
+        )
+
+    df_summary = pd.read_csv(args.summary, sep='\t')
+    df_summary.columns = df_summary.columns.str.replace(r'(_busco|_checkm2|_checkm|_gtdbtk|_gunc|_quast)$', '', regex=True)
+    for i in range(len(df_summary["bin"])):
+        name = df_summary["bin"][i]
+        name = re.sub(r'\.(fa|fasta)(\..*)?$', '', name)
+        df_summary.at[i,"bin"] = name
+        df_summary = df_summary.sort_values(by='bin')
+        df_summary["bin"] = df_summary["bin"].astype(str)
+
+    df_gunc = pd.read_csv(args.gunc_summary, sep='\t')
+    df_gunc["genome"] = df_gunc["genome"].astype(str)
+    df_gunc = df_gunc.sort_values(by='genome')
+
+    df_summary = pd.merge(df_summary, df_gunc, left_on='bin', right_on='genome', how='left')
+
+    df_summary.rename(columns={'bin': 'Bin'}, inplace=True)
+    columns_to_remove = ['Name', "genome", 'Input_file', 'Assembly', 'Bin Id']
+    df_summary = df_summary.drop(columns=columns_to_remove, errors="ignore")
+
+    df_summary['sample'] = None
+    for f in range(len(df_summary["Bin"])):
+        match = re.search(r'^.*?-.*?-(.*)$', df_summary["Bin"][f])
+        if match:
+            name = match.group(1)
+            name = re.sub(r'\.(unbinned|noclass)(\..*)?$', '', name)
+            name = re.sub(r'\.\d+(\.[^.]+)?$', '', name)
+            df_summary.at[f,"sample"] = name
+
+    df_summary.to_csv(args.out, sep="\t", index=True)
+
+if __name__ == "__main__":
+    sys.exit(main())
@@ -202,6 +202,7 @@ def main(args=None):
             "Coding_Density",
             "Translation_Table_Used",
             "Total_Coding_Sequences",
+            "Genome_Size"
         ]
         checkm2_results = pd.read_csv(
             args.checkm2_summary, usecols=use_columns, sep="\t"

@@ -990,4 +990,13 @@ process {
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
     }
+    withName: BIGMAG {
+        publishDir = [
+            [
+                path: { "${params.outdir}/GenomeBinning/BIgMAG/" },
+                mode: params.publish_dir_mode,
+                pattern: '*.tsv',
+            ]
+        ]
+    }
 }
@@ -55,8 +55,10 @@ params {
 
     // TODO: enable when we have a suitable way to run a small test
     // GUNC fails with exit code 1 if no matches, see https://github.com/grp-bork/gunc/issues/42
+    // To generate the BIgMAG file, it is necessary to include GUNC in the execution
     run_gunc                        = false
     gunc_db                         = params.pipelines_testdata_base_path + 'mag/databases/gunc/gunc-mock.dmnd'
+    //generate_bigmag_file          = true
 
     skip_metaeuk                    = false
     metaeuk_mmseqs_db               = 'Kalamari'

@@ -843,6 +843,17 @@ Note that in contrast to the other tools, for CheckM the bin name given in the c
 
 All columns other than the primary `bin` key column, and the `Depth <sample name>` columns, will include a suffix specifying from which bin QC tool the column is derived from to distinguish identically named columns from different tools.
 
+## Summary file to be used as input for BIgMAG
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `GenomeBinning/BIgMAG/bigmag_summary.tsv`: Summary of bin sequencing depths together with GUNC, QUAST, GTDB-Tk, BUSCO and CheckM2 results.
+
+</details>
+
+The output file in this directory is used as input for the dashboard [BIgMAG](https://github.com/jeffe107/BIgMAG) for visualisation and evaluation of MAG quality.
+
 ## Ancient DNA
 
 Optional, only running when parameter `-profile ancient_dna` is specified.

@@ -543,3 +543,9 @@ Up until version 4.0.0, this pipeline offered raw read taxonomic profiling using
 This feature was removed in version 5.0.0 to strengthen the pipeline's focus on metagenome assembly and binning.
 
 If you require taxonomic profiling of raw reads, we recommend using [nf-core/taxprofiler](https://nf-co.re/taxprofiler/), which is specifically designed for taxonomic profiling of raw reads and supports a wide range of tools for this purpose.
+
+## BIgMAG compatibility
+
+With the parameter `--generate_bigmag_file` a module will be triggered to generate a file that contains the output from all of the bin-quality tools that can be uploaded to the [BIgMAG](https://github.com/jeffe107/BIgMAG) dashboard for visualising and evaluating MAGs.
+Please note that generating this file requires the parameters `--run_busco`, `--run_gunc` and `--run_checkm2`, and GTDBTk should be executed (i.e., not skipped).
+The file `bigmag_summary.tsv` located at `GenomeBinning/BIgMAG` is the only file needed to run the BIgMAG dashboard.
@@ -0,0 +1,7 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - conda-forge::python=3.10.6
+  - conda-forge::pandas=1.4.3
@@ -0,0 +1,36 @@
+process BIGMAG {
+
+    conda "conda-forge::pandas=1.4.3"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/pandas:1.4.3'
+        : 'biocontainers/pandas:1.4.3'}"
+
+    input:
+    path summary
+    path gunc_sum
+
+    output:
+    path "bigmag_summary.tsv", emit: bigmag_summary
+    path "versions.yml"   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def summary  = summary.sort().size() > 0 ? "--summary ${summary}" : ""
+    def gunc_summary  = gunc_sum.sort().size() > 0 ? "--gunc_summary ${gunc_sum}" : ""
+    """
+    bigmag_summary.py \
+        ${args} \
+        ${summary} \
+        ${gunc_summary} \
+        --out bigmag_summary.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python --version 2>&1 | sed 's/Python //g')
+        pandas: \$(python -c "import pkg_resources; print(pkg_resources.get_distribution('pandas').version)")
+    END_VERSIONS
+    """
+}
@@ -167,6 +167,7 @@ params {
     gunc_database_type                   = 'progenomes'
     gunc_db                              = null
     gunc_save_db                         = false
+    generate_bigmag_file                 = false
 
     // Reproducibility options
     megahit_fix_cpu_1                    = false

@@ -1027,6 +1027,11 @@
                     "type": "boolean",
                     "description": "Save the used GUNC reference files downloaded when not using --gunc_db parameter.",
                     "help_text": "If specified, the corresponding DIAMOND file downloaded from the GUNC server will be stored in your output directory alongside your GUNC results."
+                },
+                "generate_bigmag_file": {
+                    "type": "boolean",
+                    "description": "Make a BIgMAG input file including GUNC results.",
+                    "help_text": "It requires --run_gunc and --run_checkm2 to be executed. BINQC, GTDB-TK, QUAST nor BUSCO can't be skipped."
                 }
             }
         },

@@ -29,7 +29,7 @@ workflow BIN_QC {
     ch_busco_final_summaries = channel.empty()
     ch_checkm_final_summaries = channel.empty()
     ch_checkm2_final_summaries = channel.empty()
-
+    ch_gunc_summary = channel.empty()
 
     /*
     ================================
@@ -213,7 +213,7 @@ workflow BIN_QC {
         ch_versions.mix(GUNC_RUN.out.versions)
 
         // Make sure to keep directory in sync with modules.conf
-        GUNC_RUN.out.maxcss_level_tsv
+        ch_gunc_summary = GUNC_RUN.out.maxcss_level_tsv
             .map { _meta, gunc_summary -> gunc_summary }
             .collectFile(
                 name: "gunc_summary.tsv",
@@ -242,6 +242,7 @@ workflow BIN_QC {
     busco_summary   = ch_busco_final_summaries
     checkm_summary  = ch_checkm_final_summaries
     checkm2_summary = ch_checkm2_final_summaries
+    gunc_summary    = ch_gunc_summary
     multiqc_files   = ch_multiqc_files
     versions        = ch_versions
 }
@@ -396,6 +396,11 @@ def validateInputParameters(hybrid) {
     if (params.prokka_with_compliance && !params.prokka_compliance_centre) {
         error('[nf-core/mag] ERROR: Invalid parameter combination: running PROKKA with compliance mode requires a centre name specified with `--prokka_compliance_centre <XYZ>`!')
     }
+
+    // Check BIgMAG parameters
+    if (params.generate_bigmag_file && (!params.run_gunc || !params.run_checkm2 || !params.run_busco || params.skip_gtdbtk || params.skip_quast || params.skip_binqc)) {
+        error('[nf-core/mag] ERROR: To generate the BIgMAG file you need to include the parameters `--run_checkm2` and `--run_gunc`, and you cannot skip BINQC, GTDB-TK, QUAST nor BUSCO.')
+    }
 }
 
 //

@@ -240,15 +240,15 @@
                 "MEGAHIT-MetaBAT2-prokarya-unrefined-group-0_checkm2_report.tsv:md5,ec01903b7f8a7203856a35a7bd2d4c34",
                 "checkm2_summary.tsv:md5,ec01903b7f8a7203856a35a7bd2d4c34",
                 "tiara_summary.tsv:md5,4cbfb0fd90ba48dc33d75d10c1eddb17",
-                "bin_summary.tsv:md5,e6a07c3280c6db0f7822688559afb053",
+                "bin_summary.tsv:md5,cf879345b96d29b5b8584795504b81cf",
                 "bin_depths_summary.tsv:md5,a73f2fc180a2c52038c88fbbfa6a95c3"
             ]
         ],
         "meta": {
             "nf-test": "0.9.3",
             "nextflow": "25.10.0"
         },
-        "timestamp": "2025-11-16T01:37:18.534799185"
+        "timestamp": "2025-11-28T14:15:43.756748108"
     },
     "multiqc": {
         "content": [

@@ -42,6 +42,7 @@ include { QUAST                           } from '../modules/local/quast_run/mai
 include { QUAST_BINS                      } from '../modules/local/quast_bins/main'
 include { QUAST_BINS_SUMMARY              } from '../modules/local/quast_bins_summary/main'
 include { BIN_SUMMARY                     } from '../modules/local/bin_summary/main'
+include { BIGMAG                          } from '../modules/local/bigmag/main'
 
 workflow MAG {
     take:
@@ -474,6 +475,14 @@ workflow MAG {
             )
             ch_versions = ch_versions.mix(BIN_SUMMARY.out.versions)
         }
+        if (params.generate_bigmag_file ) {
+            BIGMAG(
+                   BIN_SUMMARY.out.summary,
+                   BIN_QC.out.gunc_summary
+                   )
+            ch_bigmag_summary = BIGMAG.out.bigmag_summary
+            ch_versions = ch_versions.mix(BIGMAG.out.versions)
+        }
 
         /*
          * Prokka: Genome annotation